4 papers
CoreEditor: Correspondence-constrained Diffusion for Consistent 3D Editing
Zhe Zhu, Honghua Chen, Peng Li +1
Text-driven 3D editing seeks to modify 3D scenes according to textual descriptions, and most existing approaches tackle this by adapting pre-trained 2D image editors to multi-view…
ColorGS: High-fidelity Surgical Scene Reconstruction with Colored Gaussian Splatting
Qun Ji, Peng Li, Mingqiang Wei
High-fidelity reconstruction of deformable tissues from endoscopic videos remains challenging due to the limitations of existing methods in capturing subtle color variations and mo…
PointCG: Self-supervised Point Cloud Learning via Joint Completion and Generation
Yun Liu, Peng Li, Xuefeng Yan +6
The core of self-supervised point cloud learning lies in setting up appropriate pretext tasks, to construct a pre-training framework that enables the encoder to perceive 3D objects…
Efficient Deep Learning Board: Training Feedback Is Not All You Need
Lina Gong, Qi Gao, Peng Li +2
Current automatic deep learning (i.e., AutoDL) frameworks rely on training feedback from actual runs, which often hinder their ability to provide quick and clear performance predic…